From: Christoph Hellwig <hch@lst.de>
To: Brian Foster <bfoster@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>,
linux-xfs@vger.kernel.org, darrick.wong@oracle.com
Subject: Re: [PATCH 2/3] xfs: go straight to real allocations for direct I/O COW writes
Date: Tue, 24 Jan 2017 09:37:32 +0100 [thread overview]
Message-ID: <20170124083732.GA17818@lst.de> (raw)
In-Reply-To: <20161207194634.GE23106@bfoster.bfoster>
On Wed, Dec 07, 2016 at 02:46:34PM -0500, Brian Foster wrote:
> Only for end_fsb... xfs_bmap_btalloc() calls xfs_bmap_extsize_align()
> with the alignment, which rounds out the start and end offsets.
... and corrupts data in the direct I/O case.
The problem is that the down-alignment in xfs_bmap_extsize_align will
now create a real extent that spans before the extent that we have
to COW in this write_begin call. But the area before might have been
a hole before the dio write that had just before been filled with
an allocation in the data fork. And due to the direct I/O end_io
interface that only covers the range of the whole write we don't
know at that point where exactly the COW operation started and will
happily splice back our front pad into the data fork, replacing
the just written data with garbage. xfs/228 and sometimes generic/199
reproduce this nicely.
next prev parent reply other threads:[~2017-01-24 8:37 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-05 21:05 reflink COW improvements Christoph Hellwig
2016-12-05 21:05 ` [PATCH 1/3] xfs: reject all unaligned direct writes to reflinked files Christoph Hellwig
2016-12-07 18:59 ` Brian Foster
2016-12-05 21:05 ` [PATCH 2/3] xfs: go straight to real allocations for direct I/O COW writes Christoph Hellwig
2016-12-07 19:00 ` Brian Foster
2016-12-07 19:37 ` Christoph Hellwig
2016-12-07 19:46 ` Brian Foster
2016-12-08 4:23 ` Darrick J. Wong
2017-01-24 8:37 ` Christoph Hellwig [this message]
2017-01-24 13:50 ` Brian Foster
2017-01-24 13:59 ` Christoph Hellwig
2017-01-24 15:02 ` Brian Foster
2017-01-24 15:09 ` Christoph Hellwig
2017-01-24 16:17 ` Brian Foster
2017-01-24 16:21 ` Christoph Hellwig
2017-01-24 17:43 ` Brian Foster
2017-01-24 20:08 ` Christoph Hellwig
2017-01-24 20:10 ` Christoph Hellwig
2017-01-25 0:09 ` Darrick J. Wong
2017-01-27 17:44 ` Darrick J. Wong
2017-01-27 17:48 ` Christoph Hellwig
2016-12-05 21:05 ` [PATCH 3/3] xfs: allocate direct I/O COW blocks in iomap_begin Christoph Hellwig
2016-12-06 2:09 ` reflink COW improvements Darrick J. Wong
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170124083732.GA17818@lst.de \
--to=hch@lst.de \
--cc=bfoster@redhat.com \
--cc=darrick.wong@oracle.com \
--cc=linux-xfs@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.